Searching the druggable genome using large language models.

Large language models accessing the DGIdb API via the MCP server significantly enhance their ability to answer up-to-date biomedical questions about the druggable genome.

• Why it matters: Understanding druggable genes is crucial for drug discovery and clinical research, but current tools require complex query translation, limiting accessibility for many users.
• What they did: The authors developed the DGIdb Model Context Protocol (MCP) server, enabling large language models to interact directly with the DGIdb API through natural language queries, improving information retrieval.
• The result: This approach improves LLM performance in biomedical question-answering, facilitating more accurate and efficient exploration of drug-gene interactions, and broadening research and clinical applications.